Skip to content

RobotsVideosComponentsPapersBlogOpen SourceWorld ModelsLeaderboardIndustry ChainInvest

Robots Videos Components Papers Blog Open Source World Models Leaderboard Industry Chain Invest

physical-ai

[●●●]FETCHING

RobotWorld

Robotics knowledge and video hub · © 2026

@McQueenFuFollow Tags About662 demos289 papers871 components

Agentic Real2Sim: reconstructing a physics simulator from a single video

Loading video

Loading video

Agentic Real2Sim lets a vision-language agent reconstruct an editable, executable physics simulator from a single real-world video, instead of learning physics directly from video.

world model Agentic Real2Sim physics simulation VLA research Twitter

Category: research

Author: @robotsdigest

Date: 2026-07-22T00:00:00

Duration: 254.72s

Source: https://x.com/robotsdigest/status/2079981083622576623

Related Videos

Why Reward-Based RL Is Extremely Sample Inefficient

Why Reward-Based RL Is Extremely Sample Inefficient

@cybernetic_lab · 6 views · 2026-07-31

强化学习reinforcement learningsample efficiency

FLUX 3: Black Forest Labs launches real world model

FLUX 3: Black Forest Labs launches real world model

@shao__meng · 14 views · 2026-07-24

FLUX 3Black Forest Labs世界模型

Astribot releases Lumo-2 World-Action Model

Astribot releases Lumo-2 World-Action Model

@LeoKharon · 8 views · 2026-07-23

世界动作模型WAMLumo-2

AlayaWorld: Long-horizon playable video world generation (15B)

AlayaWorld: Long-horizon playable video world generation (15B)

@kwangmoo_yi · 4 views · 2026-07-22

world modelAlayaWorld视频生成

ABot-World-0: Infinite interactive world rollout on a single desktop GPU

ABot-World-0: Infinite interactive world rollout on a single desktop GPU

@_akhaliq · 3 views · 2026-07-22

world modelABot-World-0视频生成

Patch Policy: pretrained ViT beats OpenVLA-OFT with 0.7% params

Patch Policy: pretrained ViT beats OpenVLA-OFT with 0.7% params

@jeffacce · 4 views · 2026-07-22

VLAPatch PolicyViT